Learning to generate one-sentence biographies from Wikidata

Andrew Chisholm, Will Radford, Ben Hachey


Abstract
We investigate the generation of one-sentence Wikipedia biographies from facts derived from Wikidata slot-value pairs. We train a recurrent neural network sequence-to-sequence model with attention to select facts and generate textual summaries. Our model incorporates a novel secondary objective that helps ensure it generates sentences that contain the input facts. The model achieves a BLEU score of 41, improving significantly upon the vanilla sequence-to-sequence model and scoring roughly twice that of a simple template baseline. Human preference evaluation suggests the model is nearly as good as the Wikipedia reference. Manual analysis explores content selection, suggesting the model can trade the ability to infer knowledge against the risk of hallucinating incorrect information.
Anthology ID:
E17-1060
Volume:
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers
Month:
April
Year:
2017
Address:
Valencia, Spain
Editors:
Mirella Lapata, Phil Blunsom, Alexander Koller
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
633–642
Language:
URL:
https://aclanthology.org/E17-1060
DOI:
Bibkey:
Cite (ACL):
Andrew Chisholm, Will Radford, and Ben Hachey. 2017. Learning to generate one-sentence biographies from Wikidata. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, pages 633–642, Valencia, Spain. Association for Computational Linguistics.
Cite (Informal):
Learning to generate one-sentence biographies from Wikidata (Chisholm et al., EACL 2017)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-1/E17-1060.pdf
Code
 andychisholm/mimo